Search research articles

关于 JoVE

概览领导团队博客 JoVE 帮助中心

作者

出版流程编辑委员会范围与政策同行评审常见问题投稿

图书馆员

用户评价订阅访问资源图书馆顾问委员会常见问题

研究

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments 存档

教育

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual 教师资源中心教师网站

使用条款与条件

相关概念视频

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序

Same author

TDGF1 Mediates the Oncogenic Effects of the OLMALINC/miR-3614-5p ceRNA Axis in Colon Cancer Through Nodal/Smad2 and Glypican-1/MAPK-AKT Signaling.

Cells·2026

Same author

The Role of Defect Geometry in Localized Emission from Monolayer Tungsten Dichalcogenides.

ACS nano·2026

Same author

Technology-driven revolution in CO<sub>2</sub> fixation: From natural pathways to programmable Biosystems.

Biotechnology advances·2026

Same author

From PINNs to PIKANs: recent advances in physics-informed machine learning.

Machine learning for computational science and engineering·2026

Same author

Enterococcus faecalis Extracellular Vesicles Deliver the Bacterial GTPase Obg to Hijack mTOR Signalling in Hepatocellular Carcinoma.

Journal of extracellular vesicles·2026

Same author

Automated anatomically guided quality assessment for OCTA via multi-region analysis and statistical calibration.

Biomedical optics express·2026

Search research articles

相关实验视频

Updated: May 5, 2026

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Published on: March 2, 2015

使用神经运算符对随机机械元材料进行表征和反向设计.

Hanxun Jin¹, Boyu Zhang¹, Qianying Cao²

¹Department of Mechanical Engineering, Northwestern University, Evanston, IL, 60208, USA.

Advanced materials (Deerfield Beach, Fla.)

|April 21, 2025

概括

本研究介绍了一种机器学习 (ML) 框架,使用深度神经运算符来从有限的实验数据设计机械超材料. 这种方法使具有特定非线性机械行为材料的有效反向设计成为可能.

关键词:

在现场进行微机械实验.反向设计的设计.机械元材料是机械元材料.神经运营者是一个神经运营者.随机微观结构随机微观结构

更多相关视频

Environmental Dynamic Mechanical Analysis to Predict the Softening Behavior of Neural Implants

Environmental Dynamic Mechanical Analysis to Predict the Softening Behavior of Neural Implants

Published on: March 1, 2019

Characterizing Dissipative Elastic Metamaterials Produced by Additive Manufacturing

Characterizing Dissipative Elastic Metamaterials Produced by Additive Manufacturing

Published on: June 28, 2024

相关实验视频

Last Updated: May 5, 2026

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Published on: March 2, 2015

Environmental Dynamic Mechanical Analysis to Predict the Softening Behavior of Neural Implants

Environmental Dynamic Mechanical Analysis to Predict the Softening Behavior of Neural Implants

Published on: March 1, 2019

Characterizing Dissipative Elastic Metamaterials Produced by Additive Manufacturing

Characterizing Dissipative Elastic Metamaterials Produced by Additive Manufacturing

Published on: June 28, 2024

科学领域:

材料科学材料科学材料科学
机械工程机械工程
人工智能的人工智能

背景情况:

机器学习 (ML) 为设计机械元材料提供了先进的功能.
目前的逆向设计方法在与数据密集型要求作斗争,特别是对于非线性微型架构材料.
由于数据限制,设计具有非线性机械行为的随机架构材料具有挑战性.

研究的目的:

使用稀疏的实验数据开发一个全面的ML框架,用于机械元材料的反向设计.
利用深度神经运算符 (例如DeepONet) 来学习微观结构与属性关系.
为了实现具有特定非线性机械反应的材料的高效设计.

主要方法:

开发了一个使用深度神经运算符 (DeepONet和变体) 的科学ML框架.
该框架从稀疏,高质量的实验数据中学习微观结构和机械反应之间的关系.
为了解释性和准确性,进行了各种神经运算子和标准神经网络的系统比较.

主要成果:

机器学习框架成功地学习了微观结构和机械响应之间的关系.
机械反应的预测错误随机旋微结构的机械反应的预测错误在5-10%之间.
该方法证明了针对目标非线性机械行为的高效反向设计能力.

结论:

深度神经运算器,结合先进的机械实验,促进复杂的微型架构材料的设计.
该框架即使在数据稀缺的情况下也有效,使得能够设计具有所需非线性特性的元材料.
这项工作推进了材料设计,为下一代超材料铺平了道路,通过实验洞察得到了信息.